mistocr 0.1.6__tar.gz

mistocr-0.1.6/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2022, fastai
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

mistocr-0.1.6/MANIFEST.in

@@ -0,0 +1,5 @@
+include settings.ini
+include LICENSE
+include CONTRIBUTING.md
+include README.md
+recursive-exclude * __pycache__

mistocr-0.1.6/PKG-INFO

@@ -0,0 +1,183 @@
+Metadata-Version: 2.4
+Name: mistocr
+Version: 0.1.6
+Summary: Simple batch OCR for PDFs using Mistral's state-of-the-art vision model
+Home-page: https://github.com/franckalbinet/mistocr
+Author: Solveit
+Author-email: nobody@fast.ai
+License: Apache Software License 2.0
+Keywords: nbdev jupyter notebook python
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: Apache Software License
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: fastcore
+Requires-Dist: mistralai
+Requires-Dist: pillow
+Requires-Dist: dotenv
+Requires-Dist: lisette
+Provides-Extra: dev
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# mistocr
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+## Why mistocr?
+
+**Performance**: Mistral’s OCR delivers state-of-the-art accuracy on
+complex documents including tables, charts, and multi-column layouts.
+
+**Scale**: Process entire folders of PDFs in a single batch job. Upload
+once, process asynchronously, and retrieve results when ready - perfect
+for large document sets.
+
+**Cost savings**: Batch OCR mode reduces costs from \$1/1000 pages to
+\$0.50/1000 pages - a 50% reduction compared to synchronous processing.
+
+**Simplicity**: A single
+[`ocr()`](https://franckalbinet.github.io/mistocr/core.html#ocr)
+function handles everything - uploading, batch submission, polling for
+completion, and saving results as markdown with extracted images.
+Process one PDF or an entire folder with the same simple interface.
+
+**Organized output**: Each PDF is automatically saved to its own folder
+with pages as separate markdown files and images in an `img` subfolder,
+making results easy to navigate and process further.
+
+## Installation
+
+Install latest from the GitHub
+[repository](https://github.com/franckalbinet/mistocr):
+
+``` sh
+$ pip install git+https://github.com/franckalbinet/mistocr.git
+```
+
+or from [pypi](https://pypi.org/project/mistocr/)
+
+``` sh
+$ pip install mistocr
+```
+
+## How to use
+
+### Basic usage
+
+Process a single PDF:
+
+``` python
+from mistocr.core import ocr
+
+fname = 'files/test/attention-is-all-you-need.pdf'
+result = ocr(fname)
+```
+
+Or process an entire folder:
+
+``` python
+results = ocr('files/test')
+```
+
+### Output structure
+
+Each PDF is saved to its own folder with pages as separate markdown
+files and images in an `img` subfolder:
+
+    files/test/md/
+    ├── attention-is-all-you-need/
+    │   ├── img/
+    │   │   ├── img-0.jpeg
+    │   │   ├── img-1.jpeg
+    │   │   └── ...
+    │   ├── page_1.md
+    │   ├── page_2.md
+    │   └── ...
+    └── resnet/
+        ├── img/
+        └── ...
+
+### Reading results
+
+Read all pages from a processed PDF:
+
+``` python
+from mistocr.core import read_pgs
+
+text = read_pgs('files/test/md/attention-is-all-you-need')
+```
+
+Or read a specific page:
+
+``` python
+text = read_pgs('files/test/md/attention-is-all-you-need', 10)
+```
+
+### Customization
+
+Customize output directory, image inclusion, and polling interval:
+
+``` python
+results = ocr('files/test', out_dir='output', inc_img=False, poll_interval=5)
+```
+
+**Parameters:**
+
+- **`path`**: A single PDF file or folder containing multiple PDFs
+- **`out_dir`**: Directory name for saving markdown output (default:
+  `'md'`)
+- **`inc_img`**: Include extracted images in the output (default:
+  `True`)
+- **`key`**: Your Mistral API key (uses `MISTRAL_API_KEY` environment
+  variable if not provided)
+- **`poll_interval`**: Seconds between batch job status checks (default:
+  `2`)
+
+**Returns:** List of paths to the generated markdown files
+
+## Developer Guide
+
+If you are new to using `nbdev` here are some useful pointers to get you
+started.
+
+### Install mistocr in Development mode
+
+``` sh
+# make sure mistocr package is installed in development mode
+$ pip install -e .
+
+# make changes under nbs/ directory
+# ...
+
+# compile to have changes apply to mistocr
+$ nbdev_prepare
+```
+
+### Documentation
+
+Documentation can be found hosted on this GitHub
+[repository](https://github.com/franckalbinet/mistocr)’s
+[pages](https://franckalbinet.github.io/mistocr/). Additionally you can
+find package manager specific guidelines on
+[conda](https://anaconda.org/franckalbinet/mistocr) and
+[pypi](https://pypi.org/project/mistocr/) respectively.

mistocr-0.1.6/README.md

@@ -0,0 +1,143 @@
+# mistocr
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+## Why mistocr?
+
+**Performance**: Mistral’s OCR delivers state-of-the-art accuracy on
+complex documents including tables, charts, and multi-column layouts.
+
+**Scale**: Process entire folders of PDFs in a single batch job. Upload
+once, process asynchronously, and retrieve results when ready - perfect
+for large document sets.
+
+**Cost savings**: Batch OCR mode reduces costs from \$1/1000 pages to
+\$0.50/1000 pages - a 50% reduction compared to synchronous processing.
+
+**Simplicity**: A single
+[`ocr()`](https://franckalbinet.github.io/mistocr/core.html#ocr)
+function handles everything - uploading, batch submission, polling for
+completion, and saving results as markdown with extracted images.
+Process one PDF or an entire folder with the same simple interface.
+
+**Organized output**: Each PDF is automatically saved to its own folder
+with pages as separate markdown files and images in an `img` subfolder,
+making results easy to navigate and process further.
+
+## Installation
+
+Install latest from the GitHub
+[repository](https://github.com/franckalbinet/mistocr):
+
+``` sh
+$ pip install git+https://github.com/franckalbinet/mistocr.git
+```
+
+or from [pypi](https://pypi.org/project/mistocr/)
+
+``` sh
+$ pip install mistocr
+```
+
+## How to use
+
+### Basic usage
+
+Process a single PDF:
+
+``` python
+from mistocr.core import ocr
+
+fname = 'files/test/attention-is-all-you-need.pdf'
+result = ocr(fname)
+```
+
+Or process an entire folder:
+
+``` python
+results = ocr('files/test')
+```
+
+### Output structure
+
+Each PDF is saved to its own folder with pages as separate markdown
+files and images in an `img` subfolder:
+
+    files/test/md/
+    ├── attention-is-all-you-need/
+    │   ├── img/
+    │   │   ├── img-0.jpeg
+    │   │   ├── img-1.jpeg
+    │   │   └── ...
+    │   ├── page_1.md
+    │   ├── page_2.md
+    │   └── ...
+    └── resnet/
+        ├── img/
+        └── ...
+
+### Reading results
+
+Read all pages from a processed PDF:
+
+``` python
+from mistocr.core import read_pgs
+
+text = read_pgs('files/test/md/attention-is-all-you-need')
+```
+
+Or read a specific page:
+
+``` python
+text = read_pgs('files/test/md/attention-is-all-you-need', 10)
+```
+
+### Customization
+
+Customize output directory, image inclusion, and polling interval:
+
+``` python
+results = ocr('files/test', out_dir='output', inc_img=False, poll_interval=5)
+```
+
+**Parameters:**
+
+- **`path`**: A single PDF file or folder containing multiple PDFs
+- **`out_dir`**: Directory name for saving markdown output (default:
+  `'md'`)
+- **`inc_img`**: Include extracted images in the output (default:
+  `True`)
+- **`key`**: Your Mistral API key (uses `MISTRAL_API_KEY` environment
+  variable if not provided)
+- **`poll_interval`**: Seconds between batch job status checks (default:
+  `2`)
+
+**Returns:** List of paths to the generated markdown files
+
+## Developer Guide
+
+If you are new to using `nbdev` here are some useful pointers to get you
+started.
+
+### Install mistocr in Development mode
+
+``` sh
+# make sure mistocr package is installed in development mode
+$ pip install -e .
+
+# make changes under nbs/ directory
+# ...
+
+# compile to have changes apply to mistocr
+$ nbdev_prepare
+```
+
+### Documentation
+
+Documentation can be found hosted on this GitHub
+[repository](https://github.com/franckalbinet/mistocr)’s
+[pages](https://franckalbinet.github.io/mistocr/). Additionally you can
+find package manager specific guidelines on
+[conda](https://anaconda.org/franckalbinet/mistocr) and
+[pypi](https://pypi.org/project/mistocr/) respectively.

mistocr-0.1.6/mistocr/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.6"

mistocr-0.1.6/mistocr/_modidx.py

@@ -0,0 +1,31 @@
+# Autogenerated by nbdev
+
+d = { 'settings': { 'branch': 'main',
+                'doc_baseurl': '/mistocr',
+                'doc_host': 'https://franckalbinet.github.io',
+                'git_url': 'https://github.com/franckalbinet/mistocr',
+                'lib_path': 'mistocr'},
+  'syms': { 'mistocr.core': { 'mistocr.core._get_paths': ('core.html#_get_paths', 'mistocr/core.py'),
+                              'mistocr.core._prep_batch': ('core.html#_prep_batch', 'mistocr/core.py'),
+                              'mistocr.core._run_batch': ('core.html#_run_batch', 'mistocr/core.py'),
+                              'mistocr.core.create_batch_entry': ('core.html#create_batch_entry', 'mistocr/core.py'),
+                              'mistocr.core.download_results': ('core.html#download_results', 'mistocr/core.py'),
+                              'mistocr.core.get_api_key': ('core.html#get_api_key', 'mistocr/core.py'),
+                              'mistocr.core.ocr': ('core.html#ocr', 'mistocr/core.py'),
+                              'mistocr.core.prep_pdf_batch': ('core.html#prep_pdf_batch', 'mistocr/core.py'),
+                              'mistocr.core.read_pgs': ('core.html#read_pgs', 'mistocr/core.py'),
+                              'mistocr.core.save_images': ('core.html#save_images', 'mistocr/core.py'),
+                              'mistocr.core.save_page': ('core.html#save_page', 'mistocr/core.py'),
+                              'mistocr.core.save_pages': ('core.html#save_pages', 'mistocr/core.py'),
+                              'mistocr.core.submit_batch': ('core.html#submit_batch', 'mistocr/core.py'),
+                              'mistocr.core.upload_pdf': ('core.html#upload_pdf', 'mistocr/core.py'),
+                              'mistocr.core.wait_for_job': ('core.html#wait_for_job', 'mistocr/core.py')},
+            'mistocr.refine': { 'mistocr.refine.HeadingCorrections': ('refine.html#headingcorrections', 'mistocr/refine.py'),
+                                'mistocr.refine.add_pg_hdgs': ('refine.html#add_pg_hdgs', 'mistocr/refine.py'),
+                                'mistocr.refine.apply_hdg_fixes': ('refine.html#apply_hdg_fixes', 'mistocr/refine.py'),
+                                'mistocr.refine.fix_hdg_hierarchy': ('refine.html#fix_hdg_hierarchy', 'mistocr/refine.py'),
+                                'mistocr.refine.fix_md_hdgs': ('refine.html#fix_md_hdgs', 'mistocr/refine.py'),
+                                'mistocr.refine.fmt_hdgs_idx': ('refine.html#fmt_hdgs_idx', 'mistocr/refine.py'),
+                                'mistocr.refine.get_hdgs': ('refine.html#get_hdgs', 'mistocr/refine.py'),
+                                'mistocr.refine.mk_fixes_lut': ('refine.html#mk_fixes_lut', 'mistocr/refine.py'),
+                                'mistocr.refine.read_pgs_pg': ('refine.html#read_pgs_pg', 'mistocr/refine.py')}}}

mistocr-0.1.6/mistocr/core.py

@@ -0,0 +1,186 @@
+"""Batch OCR for PDFs using Mistral API"""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/00_core.ipynb.
+
+# %% auto 0
+__all__ = ['ocr_model', 'ocr_endpoint', 'get_api_key', 'upload_pdf', 'create_batch_entry', 'prep_pdf_batch', 'submit_batch',
+           'wait_for_job', 'download_results', 'save_images', 'save_page', 'save_pages', 'ocr', 'read_pgs']
+
+# %% ../nbs/00_core.ipynb 3
+from fastcore.all import *
+import os, re, json, time, base64, tempfile, logging
+from io import BytesIO
+from pathlib import Path
+from PIL import Image
+from mistralai import Mistral
+
+# %% ../nbs/00_core.ipynb 6
+def get_api_key(
+    key:str=None # Mistral API key
+    ):
+    "Get Mistral API key from parameter or environment"
+    key = key or os.getenv("MISTRAL_API_KEY")
+    if not key: raise ValueError("MISTRAL_API_KEY not found")
+    return key
+
+# %% ../nbs/00_core.ipynb 7
+ocr_model = "mistral-ocr-latest"
+ocr_endpoint = "/v1/ocr"
+
+# %% ../nbs/00_core.ipynb 10
+def upload_pdf(
+    path:str, # Path to PDF file
+    key:str=None # Mistral API key
+    ) -> tuple[str, Mistral]: # Mistral pdf signed url and client
+    "Upload PDF to Mistral and return signed URL"
+    c = Mistral(api_key=get_api_key(key))
+    path = Path(path)
+    uploaded = c.files.upload(file=dict(file_name=path.stem, content=path.read_bytes()), purpose="ocr")
+    return c.files.get_signed_url(file_id=uploaded.id).url, c
+
+# %% ../nbs/00_core.ipynb 15
+def create_batch_entry(
+    path:str, # Path to PDF file, 
+    url:str, # Mistral signed URL
+    cid:str=None, # Custom ID (by default using the file name without extension)
+    inc_img:bool=True # Include image in response
+    ) -> dict[str, str | dict[str, str | bool]]: # Batch entry dict
+    "Create a batch entry dict for OCR"
+    path = Path(path)
+    if not cid: cid = path.stem
+    return dict(custom_id=cid, body=dict(document=dict(type="document_url", document_url=url), include_image_base64=inc_img))
+
+# %% ../nbs/00_core.ipynb 17
+def prep_pdf_batch(
+    path:str, # Path to PDF file, 
+    cid:str=None, # Custom ID (by default using the file name without extention)
+    inc_img:bool=True, # Include image in response
+    key=None # API key
+    ) -> dict: # Batch entry dict
+    "Upload PDF and create batch entry in one step"
+    url, c = upload_pdf(path, key)
+    return create_batch_entry(path, url, cid, inc_img), c
+
+# %% ../nbs/00_core.ipynb 21
+def submit_batch(
+    entries:list[dict], # List of batch entries, 
+    c:Mistral=None, # Mistral client, 
+    model:str=ocr_model, # Model name, 
+    endpoint:str=ocr_endpoint # Endpoint name
+    ) -> dict: # Job dict
+    "Submit batch entries and return job"
+    with tempfile.NamedTemporaryFile(mode='w', suffix='.jsonl', delete=True) as f:
+        for e in entries: f.write(json.dumps(e) + '\n')
+        f.flush()
+        batch_data = c.files.upload(file=dict(file_name="batch.jsonl", content=open(f.name, "rb")), purpose="batch")
+    return c.batch.jobs.create(input_files=[batch_data.id], model=model, endpoint=endpoint)
+
+# %% ../nbs/00_core.ipynb 24
+def wait_for_job(
+    job:dict, # Job dict, 
+    c:Mistral=None, # Mistral client, 
+    poll_interval:int=10 # Poll interval in seconds
+    ) -> dict: # Job dict (with status)  
+    "Poll job until completion and return final job status"
+    while job.status in ["QUEUED", "RUNNING"]:
+        time.sleep(poll_interval)
+        job = c.batch.jobs.get(job_id=job.id)
+    return job
+
+# %% ../nbs/00_core.ipynb 26
+def download_results(
+    job:dict, # Job dict, 
+    c:Mistral=None # Mistral client
+    ) -> list[dict]: # List of results
+    "Download and parse batch job results"
+    content = c.files.download(file_id=job.output_file).read().decode('utf-8')
+    return [json.loads(line) for line in content.strip().split('\n') if line]
+
+# %% ../nbs/00_core.ipynb 31
+def save_images(
+    page:dict, # Page dict, 
+    img_dir:str='img' # Directory to save images
+    ) -> None:
+    "Save all images from a page to directory"
+    for img in page.get('images', []):
+        if img.get('image_base64') and img.get('id'):
+            img_bytes = base64.b64decode(img['image_base64'].split(',')[1])
+            Image.open(BytesIO(img_bytes)).save(img_dir / img['id'])
+
+# %% ../nbs/00_core.ipynb 32
+def save_page(
+    page:dict, # Page dict, 
+    dst:str, # Directory to save page
+    img_dir:str='img' # Directory to save images
+    ) -> None:
+    "Save single page markdown and images"
+    (dst / f"page_{page['index']+1}.md").write_text(page['markdown'])
+    if page.get('images'):
+        img_dir.mkdir(exist_ok=True)
+        save_images(page, img_dir)
+
+# %% ../nbs/00_core.ipynb 34
+def save_pages(
+    ocr_resp:dict, # OCR response, 
+    dst:str, # Directory to save pages, 
+    cid:str # Custom ID
+    ) -> Path: # Output directory
+    "Save markdown pages and images from OCR response to output directory"
+    dst = Path(dst) / cid
+    dst.mkdir(parents=True, exist_ok=True)
+    img_dir = dst / 'img'
+    for page in ocr_resp['pages']: save_page(page, dst, img_dir)
+    return dst
+
+# %% ../nbs/00_core.ipynb 40
+def _get_paths(path:str) -> list[Path]:
+    "Get list of PDFs from file or folder"
+    path = Path(path)
+    if path.is_file(): return [path]
+    if path.is_dir():
+        pdfs = path.ls(file_exts='.pdf')
+        if not pdfs: raise ValueError(f"No PDFs found in {path}")
+        return pdfs
+    raise ValueError(f"Path not found: {path}")
+
+# %% ../nbs/00_core.ipynb 41
+def _prep_batch(pdfs:list[Path], inc_img:bool=True, key:str=None) -> tuple[list[dict], Mistral]:
+    "Prepare batch entries for list of PDFs"
+    entries, c = [], None
+    for pdf in pdfs:
+        entry, c = prep_pdf_batch(pdf, inc_img=inc_img, key=key)
+        entries.append(entry)
+    return entries, c
+
+# %% ../nbs/00_core.ipynb 42
+def _run_batch(entries:list[dict], c:Mistral, poll_interval:int=2) -> list[dict]:
+    "Submit batch, wait for completion, and download results"
+    job = submit_batch(entries, c)
+    job = wait_for_job(job, c, poll_interval)
+    if job.status != 'SUCCESS': raise Exception(f"Job failed with status: {job.status}")
+    return download_results(job, c)
+
+# %% ../nbs/00_core.ipynb 43
+def ocr(
+    path:str, # Path to PDF file or folder,
+    dst:str='md', # Directory to save markdown pages, 
+    inc_img:bool=True, # Include image in response, 
+    key:str=None, # API key, 
+    poll_interval:int=2 # Poll interval in seconds
+    ) -> list[Path]: # List of output directories
+    "OCR a PDF file or folder of PDFs and save results"
+    pdfs = _get_paths(path)
+    entries, c = _prep_batch(pdfs, inc_img, key)
+    results = _run_batch(entries, c, poll_interval)
+    return L([save_pages(r['response']['body'], dst, r['custom_id']) for r in results])
+
+# %% ../nbs/00_core.ipynb 48
+def read_pgs(
+    path:str, # OCR output directory, 
+    join:bool=True # Join pages into single string
+    ) -> str|list[str]: # Joined string or list of page contents
+    "Read specific page or all pages from OCR output directory"
+    path = Path(path)
+    pgs = sorted(path.glob('page_*.md'), key=lambda p: int(p.stem.split('_')[1]))
+    contents = L([p.read_text() for p in pgs])
+    return '\n\n'.join(contents) if join else contents

mistocr-0.1.6/mistocr/refine.py

@@ -0,0 +1,143 @@
+"""Postprocess markdown files by fixing heading hierarchy and describint images"""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/01_refine.ipynb.
+
+# %% auto 0
+__all__ = ['prompt_fix_hdgs', 'get_hdgs', 'add_pg_hdgs', 'read_pgs_pg', 'fmt_hdgs_idx', 'HeadingCorrections', 'fix_hdg_hierarchy',
+           'mk_fixes_lut', 'apply_hdg_fixes', 'fix_md_hdgs']
+
+# %% ../nbs/01_refine.ipynb 3
+from fastcore.all import *
+from .core import read_pgs
+from re import sub, findall, MULTILINE
+from pydantic import BaseModel
+from lisette.core import completion
+from typing import Callable
+import os
+import json
+
+# %% ../nbs/01_refine.ipynb 7
+def get_hdgs(
+    md:str # Markdown file string
+    ) -> L: # L of strings
+    "Return the markdown headings"
+    # Sanitize removing '#' in python snippet if any
+    md = sub(r'```[\s\S]*?```', '', md)
+    return L(findall(r'^#{1,6} .+$', md, MULTILINE))
+
+
+
+# %% ../nbs/01_refine.ipynb 8
+def add_pg_hdgs(
+    md:str, # Markdown file string, 
+    n:int # Page number
+    ) -> str: # Markdown file string
+    "Add page number to all headings in page markdown"
+    md = sub(r'```[\s\S]*?```', '', md)
+    def repl(m): return m.group(0) + f' ... page {n}'
+    return sub(r'^#{1,6} .+$', repl, md, flags=MULTILINE)
+
+# %% ../nbs/01_refine.ipynb 12
+def read_pgs_pg(
+    path:str # Path to the markdown file
+    ) -> L: # List of markdown pages
+    "Read all pages of a markdown file and add page numbers to all headings"
+    pgs = read_pgs(path, join=False)
+    return L([add_pg_hdgs(pg, n) for n, pg in enumerate(pgs, 1)]).concat()
+
+# %% ../nbs/01_refine.ipynb 15
+def fmt_hdgs_idx(
+    hdgs: list[str] # List of markdown headings
+    ) -> str: # Formatted string with index
+    "Format the headings with index"
+    return '\n'.join(f"{i}. {h}" for i, h in enumerate(hdgs))
+
+
+# %% ../nbs/01_refine.ipynb 18
+class HeadingCorrections(BaseModel):
+    corrections: dict[int, str]  # index → corrected heading
+
+# %% ../nbs/01_refine.ipynb 20
+prompt_fix_hdgs = """Fix markdown heading hierarchy errors while preserving the document's intended structure.
+
+INPUT FORMAT: Each heading is prefixed with its index number (e.g., "0. # Title ... page 1")
+
+RULES - Apply these fixes in order:
+
+1. **Single H1 rule**: Documents must have exactly ONE # heading (typically the document title at the top)
+   - If index 0 is already #, then all subsequent headings (index 1+) must be ## or deeper
+   - If no H1 exists, the first major heading should be #, and all others ## or deeper
+   - NO exceptions: appendices, references, and all sections are ## or deeper after the title
+
+2. **Infer depth from numbering patterns**: If headings contain section numbers, deeper nesting means deeper heading level
+   - Parent section (e.g., "1", "2", "A") should be shallower than child (e.g., "1.1", "2.a", "A.1")
+   - Child section should be one # deeper than parent
+   - Works with any numbering: "1/1.1/1.1.1", "A/A.1/A.1.a", "I/I.A/I.A.1", etc.
+
+3. **Level jumps**: Headings can only increase by one # at a time when moving deeper
+   - Wrong: ## Section → ##### Subsection
+   - Fixed: ## Section → ### Subsection
+
+4. **Decreasing levels is OK**: Moving back up the hierarchy (### to ##) is valid for new sections
+
+OUTPUT: Return a Python dictionary mapping index to corrected heading (without the index prefix).
+IMPORTANT: Preserve the " ... page N" suffix in all corrected headings.
+Only include entries that need changes.
+
+Headings to analyze:
+{headings_list}
+"""
+
+
+# %% ../nbs/01_refine.ipynb 22
+def fix_hdg_hierarchy(
+    hdgs: list[str], # List of markdown headings
+    prompt: str=None, # Prompt to use
+    model: str='claude-sonnet-4-5', # Model to use
+    api_key: str=None # API key
+    ) -> dict[int, str]: # Dictionary of index → corrected heading
+    "Fix the heading hierarchy"
+    if api_key is None: api_key = os.getenv('ANTHROPIC_API_KEY')
+    if prompt is None: prompt = prompt_fix_hdgs
+    prompt = prompt.format(headings_list=fmt_hdgs_idx(hdgs))
+    r = completion(model=model, messages=[{"role": "user", "content": prompt}], response_format=HeadingCorrections, api_key=api_key)
+    return json.loads(r.choices[0].message.content)['corrections']
+
+
+# %% ../nbs/01_refine.ipynb 25
+@delegates(fix_hdg_hierarchy)
+def mk_fixes_lut(
+    hdgs: list[str], # List of markdown headings
+    model: str='claude-sonnet-4-5', # Model to use
+    api_key: str=None, # API key
+    **kwargs
+    ) -> dict[str, str]: # Dictionary of old → new heading
+    "Make a lookup table of fixes"
+    if api_key is None: api_key = os.getenv('ANTHROPIC_API_KEY')
+    fixes = fix_hdg_hierarchy(hdgs, model=model, api_key=api_key, **kwargs)
+    return {hdgs[int(k)]:v for k,v in fixes.items()}
+
+# %% ../nbs/01_refine.ipynb 28
+def apply_hdg_fixes(
+    p:str, # Page to fix
+    lut_fixes: dict[str, str], # Lookup table of fixes
+    ) -> str: # Page with fixes applied
+    "Apply the fixes to the page"
+    for old in get_hdgs(p): p = p.replace(old, lut_fixes.get(old, old))
+    return p
+
+# %% ../nbs/01_refine.ipynb 31
+@delegates(mk_fixes_lut)
+def fix_md_hdgs(
+    src:str, # Source directory with markdown pages
+    model:str='claude-sonnet-4-5', # Model
+    dst:str=None, # Destination directory (None=overwrite)
+    **kwargs
+):
+    "Fix heading hierarchy in markdown document"
+    src_path,dst_path = Path(src),Path(dst) if dst else Path(src)
+    if dst_path != src_path: dst_path.mkdir(parents=True, exist_ok=True)
+    pgs_with_pg = read_pgs_pg(src_path)
+    lut = mk_fixes_lut(L([get_hdgs(pg) for pg in pgs_with_pg]).concat(), model, **kwargs)
+    for i,p in enumerate(pgs_with_pg, 1):
+        (dst_path/f'page_{i}.md').write_text(apply_hdg_fixes(p, lut))

mistocr-0.1.6/mistocr.egg-info/PKG-INFO

@@ -0,0 +1,183 @@
+Metadata-Version: 2.4
+Name: mistocr
+Version: 0.1.6
+Summary: Simple batch OCR for PDFs using Mistral's state-of-the-art vision model
+Home-page: https://github.com/franckalbinet/mistocr
+Author: Solveit
+Author-email: nobody@fast.ai
+License: Apache Software License 2.0
+Keywords: nbdev jupyter notebook python
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: Apache Software License
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: fastcore
+Requires-Dist: mistralai
+Requires-Dist: pillow
+Requires-Dist: dotenv
+Requires-Dist: lisette
+Provides-Extra: dev
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# mistocr
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+## Why mistocr?
+
+**Performance**: Mistral’s OCR delivers state-of-the-art accuracy on
+complex documents including tables, charts, and multi-column layouts.
+
+**Scale**: Process entire folders of PDFs in a single batch job. Upload
+once, process asynchronously, and retrieve results when ready - perfect
+for large document sets.
+
+**Cost savings**: Batch OCR mode reduces costs from \$1/1000 pages to
+\$0.50/1000 pages - a 50% reduction compared to synchronous processing.
+
+**Simplicity**: A single
+[`ocr()`](https://franckalbinet.github.io/mistocr/core.html#ocr)
+function handles everything - uploading, batch submission, polling for
+completion, and saving results as markdown with extracted images.
+Process one PDF or an entire folder with the same simple interface.
+
+**Organized output**: Each PDF is automatically saved to its own folder
+with pages as separate markdown files and images in an `img` subfolder,
+making results easy to navigate and process further.
+
+## Installation
+
+Install latest from the GitHub
+[repository](https://github.com/franckalbinet/mistocr):
+
+``` sh
+$ pip install git+https://github.com/franckalbinet/mistocr.git
+```
+
+or from [pypi](https://pypi.org/project/mistocr/)
+
+``` sh
+$ pip install mistocr
+```
+
+## How to use
+
+### Basic usage
+
+Process a single PDF:
+
+``` python
+from mistocr.core import ocr
+
+fname = 'files/test/attention-is-all-you-need.pdf'
+result = ocr(fname)
+```
+
+Or process an entire folder:
+
+``` python
+results = ocr('files/test')
+```
+
+### Output structure
+
+Each PDF is saved to its own folder with pages as separate markdown
+files and images in an `img` subfolder:
+
+    files/test/md/
+    ├── attention-is-all-you-need/
+    │   ├── img/
+    │   │   ├── img-0.jpeg
+    │   │   ├── img-1.jpeg
+    │   │   └── ...
+    │   ├── page_1.md
+    │   ├── page_2.md
+    │   └── ...
+    └── resnet/
+        ├── img/
+        └── ...
+
+### Reading results
+
+Read all pages from a processed PDF:
+
+``` python
+from mistocr.core import read_pgs
+
+text = read_pgs('files/test/md/attention-is-all-you-need')
+```
+
+Or read a specific page:
+
+``` python
+text = read_pgs('files/test/md/attention-is-all-you-need', 10)
+```
+
+### Customization
+
+Customize output directory, image inclusion, and polling interval:
+
+``` python
+results = ocr('files/test', out_dir='output', inc_img=False, poll_interval=5)
+```
+
+**Parameters:**
+
+- **`path`**: A single PDF file or folder containing multiple PDFs
+- **`out_dir`**: Directory name for saving markdown output (default:
+  `'md'`)
+- **`inc_img`**: Include extracted images in the output (default:
+  `True`)
+- **`key`**: Your Mistral API key (uses `MISTRAL_API_KEY` environment
+  variable if not provided)
+- **`poll_interval`**: Seconds between batch job status checks (default:
+  `2`)
+
+**Returns:** List of paths to the generated markdown files
+
+## Developer Guide
+
+If you are new to using `nbdev` here are some useful pointers to get you
+started.
+
+### Install mistocr in Development mode
+
+``` sh
+# make sure mistocr package is installed in development mode
+$ pip install -e .
+
+# make changes under nbs/ directory
+# ...
+
+# compile to have changes apply to mistocr
+$ nbdev_prepare
+```
+
+### Documentation
+
+Documentation can be found hosted on this GitHub
+[repository](https://github.com/franckalbinet/mistocr)’s
+[pages](https://franckalbinet.github.io/mistocr/). Additionally you can
+find package manager specific guidelines on
+[conda](https://anaconda.org/franckalbinet/mistocr) and
+[pypi](https://pypi.org/project/mistocr/) respectively.

mistocr-0.1.6/mistocr.egg-info/SOURCES.txt

@@ -0,0 +1,17 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+settings.ini
+setup.py
+mistocr/__init__.py
+mistocr/_modidx.py
+mistocr/core.py
+mistocr/refine.py
+mistocr.egg-info/PKG-INFO
+mistocr.egg-info/SOURCES.txt
+mistocr.egg-info/dependency_links.txt
+mistocr.egg-info/entry_points.txt
+mistocr.egg-info/not-zip-safe
+mistocr.egg-info/requires.txt
+mistocr.egg-info/top_level.txt

mistocr-0.1.6/mistocr.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

mistocr-0.1.6/mistocr.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[nbdev]
+mistocr = mistocr._modidx:d

mistocr-0.1.6/mistocr.egg-info/not-zip-safe

@@ -0,0 +1 @@
+

mistocr-0.1.6/mistocr.egg-info/requires.txt

@@ -0,0 +1,7 @@
+fastcore
+mistralai
+pillow
+dotenv
+lisette
+
+[dev]

mistocr-0.1.6/mistocr.egg-info/top_level.txt

@@ -0,0 +1 @@
+mistocr

mistocr-0.1.6/pyproject.toml

@@ -0,0 +1,3 @@
+[build-system]
+requires = ["setuptools>=64.0"]
+build-backend = "setuptools.build_meta"

mistocr-0.1.6/settings.ini

@@ -0,0 +1,39 @@
+[DEFAULT]
+repo = mistocr
+lib_name = mistocr
+version = 0.1.6
+min_python = 3.9
+license = apache2
+black_formatting = False
+doc_path = _docs
+lib_path = mistocr
+nbs_path = nbs
+recursive = True
+tst_flags = notest
+put_version_in_init = True
+update_pyproject = True
+branch = main
+custom_sidebar = False
+doc_host = https://franckalbinet.github.io
+doc_baseurl = /mistocr
+git_url = https://github.com/franckalbinet/mistocr
+title = mistocr
+audience = Developers
+author = Solveit
+author_email = nobody@fast.ai
+copyright = 2025 onwards, Solveit
+description = Simple batch OCR for PDFs using Mistral's state-of-the-art vision model
+keywords = nbdev jupyter notebook python
+language = English
+status = 3
+user = franckalbinet
+requirements = fastcore mistralai pillow dotenv lisette
+readme_nb = index.ipynb
+allowed_metadata_keys = 
+allowed_cell_metadata_keys = 
+jupyter_hooks = False
+clean_ids = True
+clear_all = False
+cell_number = True
+skip_procs = 
+

mistocr-0.1.6/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

mistocr-0.1.6/setup.py

@@ -0,0 +1,64 @@
+from pkg_resources import parse_version
+from configparser import ConfigParser
+import setuptools, shlex
+assert parse_version(setuptools.__version__)>=parse_version('36.2')
+
+# note: all settings are in settings.ini; edit there, not here
+config = ConfigParser(delimiters=['='])
+config.read('settings.ini', encoding='utf-8')
+cfg = config['DEFAULT']
+
+cfg_keys = 'version description keywords author author_email'.split()
+expected = cfg_keys + "lib_name user branch license status min_python audience language".split()
+for o in expected: assert o in cfg, "missing expected setting: {}".format(o)
+setup_cfg = {o:cfg[o] for o in cfg_keys}
+
+licenses = {
+    'apache2': ('Apache Software License 2.0','OSI Approved :: Apache Software License'),
+    'mit': ('MIT License', 'OSI Approved :: MIT License'),
+    'gpl2': ('GNU General Public License v2', 'OSI Approved :: GNU General Public License v2 (GPLv2)'),
+    'gpl3': ('GNU General Public License v3', 'OSI Approved :: GNU General Public License v3 (GPLv3)'),
+    'bsd3': ('BSD License', 'OSI Approved :: BSD License'),
+}
+statuses = [ '1 - Planning', '2 - Pre-Alpha', '3 - Alpha',
+    '4 - Beta', '5 - Production/Stable', '6 - Mature', '7 - Inactive' ]
+py_versions = '3.6 3.7 3.8 3.9 3.10 3.11 3.12'.split()
+
+requirements = shlex.split(cfg.get('requirements', ''))
+if cfg.get('pip_requirements'): requirements += shlex.split(cfg.get('pip_requirements', ''))
+min_python = cfg['min_python']
+lic = licenses.get(cfg['license'].lower(), (cfg['license'], None))
+dev_requirements = (cfg.get('dev_requirements') or '').split()
+
+package_data = dict()
+pkg_data = cfg.get('package_data', None)
+if pkg_data:
+    package_data[cfg['lib_name']] =  pkg_data.split() # split as multiple files might be listed
+# Add package data to setup_cfg for setuptools.setup(..., **setup_cfg)
+setup_cfg['package_data'] = package_data
+
+setuptools.setup(
+    name = cfg['lib_name'],
+    license = lic[0],
+    classifiers = [
+        'Development Status :: ' + statuses[int(cfg['status'])],
+        'Intended Audience :: ' + cfg['audience'].title(),
+        'Natural Language :: ' + cfg['language'].title(),
+    ] + ['Programming Language :: Python :: '+o for o in py_versions[py_versions.index(min_python):]] + (['License :: ' + lic[1] ] if lic[1] else []),
+    url = cfg['git_url'],
+    packages = setuptools.find_packages(),
+    include_package_data = True,
+    install_requires = requirements,
+    extras_require={ 'dev': dev_requirements },
+    dependency_links = cfg.get('dep_links','').split(),
+    python_requires  = '>=' + cfg['min_python'],
+    long_description = open('README.md', encoding='utf-8').read(),
+    long_description_content_type = 'text/markdown',
+    zip_safe = False,
+    entry_points = {
+        'console_scripts': cfg.get('console_scripts','').split(),
+        'nbdev': [f'{cfg.get("lib_path")}={cfg.get("lib_path")}._modidx:d']
+    },
+    **setup_cfg)
+
+